Systems and Methods for Predicting Missing Data Values

Abstract

A method may include receiving a file with a first healthcare claim. The method may include parsing the first healthcare claim into one or more claim data elements. The method may include performing an automatic discovery process on a first claim data element of the one or more data elements. The automatic discovery process may include identifying a replacement value for the claim data element value of the first claim data element and assigning an accuracy score to the replacement value. In response to the accuracy score exceeding a pre-determined score threshold, the automatic discovery process may include replacing the claim data element value of the first claim data element with the replacement value. In response to the accuracy probability score being below the pre-determined score threshold, the automatic discovery process may include presenting the replacement value via a user interface.

What is claimed is: 
     
         1 . A non-transitory, computer-readable storage medium including executable instructions stored thereon, wherein the executable instructions, when executed by a processor, cause the processor to:
 receive a file that includes a first healthcare claim;   parse the first healthcare claim into one or more claim data elements, wherein each claim data element includes
 a claim data element field, and 
 a claim data element value corresponding to the claim data element field; and 
   perform an automatic discovery process on a first claim data element of the one or more data elements, wherein the automatic discovery process includes
 identifying a replacement value for the claim data element value of the first claim data element, 
 assigning an accuracy score to the replacement value, 
 in response to the accuracy score exceeding a pre-determined score threshold, replacing the claim data element value of the first claim data element with the replacement value, and 
 in response to the accuracy probability score being below the pre-determined score threshold, presenting the replacement value via a user interface. 
   
     
     
         2 . The computer-readable storage medium of  claim 1 , wherein the healthcare claim includes at least one of:
 a workers' compensation claim; or   a Veteran's Health Administration claim.   
     
     
         3 . The computer-readable storage medium of  claim 1 , wherein the claim data element field of the first claim data element includes at least one of:
 a payer identifier;   a claim number;   a patient first name;   a patient last name;   an employer name;   a patient government ID number;   a date of injury;   a billing location identifier; or   a subscriber relation code.   
     
     
         4 . The computer-readable storage medium of  claim 1 , wherein the processor identifying the replacement value includes the processor identifying the replacement value based on one or more claim data elements stored in a data lake. 
     
     
         5 . The computer-readable storage medium of  claim 1 , wherein the processor identifying the replacement value includes the processor identifying the replacement value based on a robot process automation (RPA) process. 
     
     
         6 . The computer-readable storage medium of  claim 5 , wherein the RPA process includes the processor:
 sending virtualized keystrokes to a login screen of a website;   sending virtualized keystrokes to a search screen of the website;   reading the replacement value from a search result screen of the website; and   storing the replacement value in a data storage in data communication with the processor.   
     
     
         7 . The computer-readable storage medium of  claim 1 , wherein the processor performing the automatic discovery process comprises the processor identifying a second healthcare claim, wherein the second healthcare claim includes a successfully processed healthcare claim. 
     
     
         8 . The computer-readable storage medium of  claim 7 , wherein the processor assigning the accuracy score to the replacement value comprises the processor generating an accuracy score based on:
 whether the replacement value matches a claim data element of the second healthcare claim; and   whether the second healthcare claim includes a payment date within a pre-determined time threshold.   
     
     
         9 . The computer-readable storage medium of  claim 8 , wherein the claim data element of the second healthcare claim comprises at least one of:
 a Social Security number;   a patient name; or   a patient birthdate.   
     
     
         10 . A method, comprising:
 receiving a file that includes a first healthcare claim;   parsing the first healthcare claim into one or more claim data elements, wherein each claim data element includes
 a claim data element field, and 
 a claim data element value corresponding to the claim data element field; and 
   performing an automatic discovery process on a first claim data element of the one or more data elements, wherein the automatic discovery process includes
 identifying a replacement value for the claim data element value of the first claim data element, 
 assigning an accuracy score to the replacement value, 
 in response to the accuracy score exceeding a pre-determined score threshold, replacing the claim data element value of the first claim data element with the replacement value, and 
 in response to the accuracy probability score being below the pre-determined score threshold, presenting the replacement value via a user interface. 
   
     
     
         11 . The method of  claim 10 , further comprising, in response to parsing the first healthcare claim, storing the one or more claim data elements in a data storage. 
     
     
         12 . The method of  claim 10 , further comprising:
 identifying a claim data element of the one or more claim data elements, wherein the identified claim data element includes an error; and   modifying the identified claim data element to correct the error.   
     
     
         13 . The method of  claim 10 , wherein performing the automatic discovery process comprises identifying a second healthcare claim, wherein the second healthcare claim is similar to the first healthcare claim. 
     
     
         14 . The method of  claim 13 , wherein:
 the second healthcare claim includes a second healthcare claim element; and   identifying the replacement value comprises selecting a claim data element value of the second claim data element as the replacement value.   
     
     
         15 . The method of  claim 10 , wherein:
 identifying the replacement value includes identifying a plurality of replacement values; and   presenting the replacement value includes presenting the plurality of replacement values via the user interface.   
     
     
         16 . The method of  claim 10 , further comprising:
 determining that a second claim data element is absent from the one or more claim data elements;   identifying a value for the second claim data element;   generating the second claim data element, wherein the second claim data element includes the identified value; and   including the second claim data element in the one or more claim data elements.   
     
     
         17 . The method of  claim 10 , wherein presenting the replacement value via the user interface comprises presenting further text information via the user interface, wherein the further text information is based on the replacement value. 
     
     
         18 . The method of  claim 10 , further comprising:
 receiving an acceptance from the user interface; and   replacing the claim data element value of the first claim data element with the replacement value.   
     
     
         19 . A system, comprising:
 a data storage; and   a server in data communication with the data storage, wherein the server includes a computer-readable storage medium including executable instructions stored thereon, wherein the executable instructions of the computer-readable medium, when executed by a processor of the server, cause the processor to:
 receive a file that includes a first healthcare claim, 
 parse the first healthcare claim into one or more claim data elements, wherein each claim data element includes
 a claim data element field, and 
 a claim data element value corresponding to the claim data element field, 
 
 store the first healthcare claim in the data storage, and 
 perform an automatic discovery process on a first claim data element of the one or more data elements, wherein the automatic discovery process includes
 identifying a replacement value for the claim data element value of the first claim data element, 
 assigning an accuracy score to the replacement value, 
 in response to the accuracy score exceeding a pre-determined score threshold, replacing the claim data element value of the first claim data element with the replacement value, and 
 in response to the accuracy probability score being below the pre-determined score threshold, presenting the replacement value via a user interface. 
 
   
     
     
         20 . The system of  claim 19 , wherein:
 the processor of the server performing the automatic discovery process includes the processor identifying a second healthcare claim, wherein the second healthcare claim is similar to the first healthcare claim;   the second healthcare claim includes a second healthcare claim element; and   identifying the replacement value comprises selecting a claim data element value of the second claim data element as the replacement value.